A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data
This work addresses the under-studied regime of sequential binding commitments in multi-party negotiations, which is incremental as it builds on existing negotiation frameworks by introducing a new benchmark and evaluation methods.
The researchers tackled the problem of evaluating decision-making in multi-party negotiations with binding commitments by creating a benchmark with a configurable game generator and testing three value-function approximations. They found that different game structures require different valuation strategies, with exact evaluation on small games and comparative evaluation on large instances from the Harvard Negotiation Challenge showing where each approximation succeeds or fails.
Many real-world multi-party negotiations unfold as sequences of binding, action-level commitments rather than a single final outcome. We introduce a benchmark for this under-studied regime featuring a configurable game generator that sweeps key structural properties such as incentive alignment, goal complexity, and payoff distribution. To evaluate decision-making, we test three value-function approximations - myopic reward, an optimistic upper bound, and a pessimistic lower bound - that act as biased lenses on deal evaluation. Through exact evaluation on small games and comparative evaluation on large, document-grounded instances derived from the Harvard Negotiation Challenge, we map the strategic regimes where each approximation succeeds or fails. We observe that different game structures demand different valuation strategies, motivating agents that learn robust state values and plan effectively over long horizons under binding commitments and terminal only rewards.